Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2156. Min Act: -0.0000

Data Index: 704345 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1144688 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1078142 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.2159. Min Act: -0.0000

Data Index: 330265 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1975. Min Act: -0.0000

Data Index: 273270 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1239903 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1887. Min Act: -0.0000

Data Index: 927059 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1813. Min Act: -0.0000

Data Index: 432459 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1150135 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1725. Min Act: -0.0000

Data Index: 18187 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1089059 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1267647 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1693. Min Act: -0.0000

Data Index: 254921 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1749. Min Act: -0.0000

Data Index: 816456 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1117170 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1784. Min Act: -0.0000

Data Index: 978864 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1783. Min Act: -0.0000

Data Index: 548326 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1780. Min Act: -0.0000

Data Index: 898077 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1231259 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.2213. Min Range: -0.2213

Max Act: 0.1694. Min Act: -0.0000

Data Index: 807050 (C4 (Web Text))

Max Activating Token Index: 97